© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43934
    Prev
    Next
    INDEX
    Explanations

    parentheses with symbols (<, >, #, %, -)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </td>
    -2.52
     (
    -2.52
    </em>
    -2.13
    Also
    -1.82
     is
    -1.70
     -
    -1.69
    ↵
    -1.68
    3
    -1.67
    u
    -1.66
     although
    -1.63
    POSITIVE LOGITS
    
    1.98
    了不少
    1.98
     paff
    1.89
     $\&$
    1.89
    Ꮴ
    1.88
    珦
    1.87
     #%
    1.83
    natura
    1.82
    ($("#
    1.80
     ftill
    1.79
    Activations Density 0.082%

    No Known Activations